IEEE Trans Cybern. 2019 Mar;49(3):734-745. doi: 10.1109/TCYB.2017.2776976. Epub 2018 May 15.
This paper concentrates on the remote state estimation problem for nonlinear systems over a communication-limited wireless sensor network. Because of the non-Gaussian property caused by nonlinear transformation, the unscented transformation technique is exploited to obtain approximate Gaussian probability distributions of state and measurement. To reduce excessive data transmission, uncontrollable and controllable stochastic event-triggered scheduling schemes are developed to decide whether the current measurement should be transmitted. Compared with some existing deterministic event-triggered scheduling schemes, the newly developed ones possess a potential superiority in maintaining Gaussian property of innovation process. Under the proposed schemes, two nonlinear state estimators are designed based on the unscented Kalman filter. Stability and convergence conditions of these two estimators are established by analyzing behaviors of estimation error and error covariance. It is shown that an expected compromise between communication rate and estimation quality can be achieved by properly tuning event-triggered parameter matrix. Numerical examples are provided to testify the validity of the proposed results.
本文专注于通信受限的无线传感器网络中非线性系统的远程状态估计问题。由于非线性变换引起的非高斯特性，使用无迹变换技术来获得状态和测量的近似高斯概率分布。为了减少过多的数据传输，开发了不可控和可控随机事件触发调度方案来决定当前的测量值是否应该传输。与一些现有的确定性事件触发调度方案相比，新开发的方案在保持创新过程的高斯特性方面具有潜在的优势。在提出的方案下，基于无迹卡尔曼滤波器设计了两个非线性状态估计器。通过分析估计误差和误差协方差的行为，建立了这两个估计器的稳定性和收敛性条件。结果表明，通过适当调整事件触发参数矩阵，可以在通信速率和估计质量之间实现预期的折衷。提供了数值示例来验证所提出结果的有效性。
